Havuz

Distributed 56M-parameter LLM inference across 3 ESP32-S3 boards via ESP-NOW , Split-PLE + KV cache, fully offline.

Deterministic memory layer for your agents

Local Python CLI for reset credits, rate-limit windows, local usage metadata, read-only online usage/profile data, and optional API organisa

Lightweight Codex/Claude/Antigravity loop harness with strict evidence gates.

A Claude Code plugin that fills your job applications from your profile, drafts the cover letter, and leaves Submit to you. Locally.

Free-first Chinese and English web search MCP using zero-key sources and inspectable evidence.

Private local meeting rooms where Codex, Claude Code, and other agents collaborate live.

🦀 Decoder-only LLM built from scratch in pure Rust using Candle — no Python, no PyTorch. Gated DeltaNet + sparse attention, fine-grained MoE

LLMs have ended reverse engineering as a high-barrier skill. Case study: reconstructing 6/7 custom HTTP signing parameters of Douyin (TikTok

Track and rotate your Claude & Codex usage across accounts from one live dashboard — read live, never spending a token.

Local-first cinematic still archive for filmmakers. Search your frames by look, mood, technique or director with SigLIP semantic search; ing

AI protocol scanner — discover exposed MCP servers, A2A Agent Cards, and open LLM APIs in one command. 一条命令盘点 MCP、A2A Agent Card 和 LLM 开放接口暴

Create motion-graphics videos from natural-language using Hyperframes. Researches topics, explains GitHub repos, renders the result.

SRA-Bench and SR-Agents: a benchmark and toolkit for skill-retrieval-augmented LLM agents.

An experimental playground for open-source, all-in-one office AI for universities: code, docs, spreadsheets, slides, browser – all are the A

A personal AI agent that can work safely on your machine, remember useful context, and keep its data under your control.

The 30 MB open-source edge AI agent runtime. Run AI agents offline on Linux (Raspberry Pi, Jetson). GPIO, UART, MQTT as first-class nodes. I

🧠 Brain-inspired cognitive architecture plugin for AI agents — persistent memory, evolving personality, neurochemistry-driven mood, learning

MCPify is an AI enablement compiler that transforms existing applications into AI-native, agent-operable systems.

600 KB WASM runtime for Cactus Compute's Needle AI tool-calling models, Needle 3, 2 and 1 from one build. Browser, Cloudflare Workers, Node.

Topic + template → short vertical video from your own B-roll: AI script, voice, scene plan, captions, FFmpeg render. Multi-persona, AI shot

Search & apply to ~4,700 salary-transparent tech jobs across 7 countries (🇨🇭🇩🇪🇬🇧🇺🇸🇨🇦🇳🇱🇫🇷) from your terminal or AI agent — zero-dependency P

ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Stream

self-extending sandboxed agentic harness. a loop, two tools and an llm

Zero-leak online detection of LLM decoding corruption and Free Web Search for your AI agents! Catch repetition loops, language drift and gar

Selfhost modern LLM stacks. Run the whole fleet from your terminal

World's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU-accelerated

BokeBox: multi-source private AI podcast studio — videos/links/articles/notes → spoken episodes. Custom persona & voice, MCP + pluggable s

AI Agent 面试知识库：覆盖 LLM、Prompt、RAG、MCP、Tool Use、Agent 架构、Multi-Agent、LangGraph、Claude Code、Codex CLI、工程化评估、安全与源码解析。

Your brain, then your team's brain, then your agents' brain. Drop in documents and it compounds them into an interlinked markdown wiki you o

Local-first AI daemon for Logseq OG: background semantic indexing, link hygiene, and agent-ready CLI/MCP — edits Markdown on disk (no cloud,

Production-grade Agent Skills for AI coding agents—composable workflows for planning, TDD, debugging, review, UI/UX, releases, incidents, an

The most frequently used agent skills of Wade Foster, CEO of Zapier

面向 PRD、业务规则、SOP、流程文档和产品截图的证据型 RAG 知识库。

Rational engineering system prompt for Codex and LLMs — focused on accuracy, software engineering, AI, security research, bug bounty, and re

Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no targ

Desktop control center for ChatGPT Codex: launch, provider switching, enhancements, repairs, and diagnostics.

A floating, screen-aware Claude Code chat for Windows - it reads your screen to answer, and runs on your own Claude subscription (no API key

Turn Claude Code into an equity-research agent: 24 analysis skills (Anthropic's open-source bundle + community), a single data MCP, and a pe

Official Findings of EMNLP 2026 implementation of Corpus2Skill: compile a document corpus into a navigable skill hierarchy that LLM agents e

AI agent skill that generates beautifully typeset travel guidebook PDFs — from research to print, powered by parallel agents and Amap MCP.

面向招投标场景的本地化 RAG 标书解析、资质匹配与红线提醒助手

Feedback widget with screenshots, annotations, and AI triage

Route-first FPV AI video prompting skill for Seedance, Kling, Runway, Veo, GPT Image asset packs, numbered stops, and red-line path control.

Local-first AI companion daemon — an agent harness with its own long-term memory. Remembers you, grows with you, extends and repairs itself.

Real-time YOLOv8n UAV detection on the RK3588S NPU | saturates the sensor at 46 FPS | ~140 MB RAM | fully hardware-accelerated (ISP+RGA+NPU)

give non-vision models the ability to see images by routing images to a vision capable model

The most comprehensive open-source MCP server for Bricks Builder — 105 tools for pages, templates, styles, SEO, content, and more.

Official Aspire skills and plugins for AI coding agents to initialize, wire, orchestrate, monitor, and deploy distributed apps.

Local outcome-loop + reward layer for coding agents — remember what worked, ship the next move, measure how it landed. Docs at nimroboai.com